Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Recommendation Reranking on Industrial streaming dataset (Discovery)
Loading...
92.9
Recall@1 Delta (%)
Rewrite + Trained Reasoner
-3.716
21.367
46.45
71.533
Feb 24, 2026
Recall@1 Delta (%)
Updated 3mo ago
Evaluation Results
Method
Method
Links
Recall@1 Delta (%)
Rewrite + Trained Reasoner
Backbone=Qwen-3 8B, Ve...
2026.02
92.9
Rewrite Verbalizer
Backbone=Qwen-3 8B, Ve...
2026.02
12.5
Action-Based Verbalizer
Backbone=Qwen-3 8B, Ve...
2026.02
10.7
Zero-Shot Verbalizer
Backbone=Qwen-3 8B, Ve...
2026.02
5.3
Template Baseline
Backbone=Qwen-3 8B
2026.02
0
Feedback
Search any
task
Search any
task